---
title: Hermes-2-Pro-Mistral-7B-3bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Hermes-2-Pro-Mistral-7B-3bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Hermes-2-Pro-Mistral-7B-3bit.md"
repository: mlx-community/Hermes-2-Pro-Mistral-7B-3bit
last_updated: 2024-12-19
license: apache-2.0
model_type:
  - mistral
architectures:
  - MistralForCausalLM
base_model:
  - NousResearch/Hermes-2-Pro-Mistral-7B
base_model_relation: quantized
parameters: 905.5M
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 986
stars: 0
tags:
  - Mistral
  - instruct
  - finetune
  - chatml
  - DPO
  - RLHF
  - gpt4
  - "synthetic data"
  - distillation
  - "function calling"
  - "json mode"
  - mlx
---

# Hermes-2-Pro-Mistral-7B-3bit

> Hermes-2-Pro-Mistral-7B-3bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Hermes-2-Pro-Mistral-7B-3bit

mlx-community/Hermes-2-Pro-Mistral-7B-3bit 是 ModelScope 魔搭社区上的 905.5M 参数机器学习模型，采用 apache-2.0 许可，基于 NousResearch/Hermes-2-Pro-Mistral-7B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Hermes-2-Pro-Mistral-7B-3bit
- **License**: apache-2.0
- **Parameters**: 905.5M
- **Base model**: NousResearch/Hermes-2-Pro-Mistral-7B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: Mistral, instruct, finetune, chatml, DPO, RLHF, gpt4, synthetic data, distillation, function calling, json mode, mlx
- **Downloads**: 986
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/Hermes-2-Pro-Mistral-7B-3bit

---

# mlx-community/Hermes-2-Pro-Mistral-7B-3bit

The Model [mlx-community/Hermes-2-Pro-Mistral-7B-3bit](https://huggingface.co/mlx-community/Hermes-2-Pro-Mistral-7B-3bit) was
converted to MLX format from [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
using mlx-lm version **0.20.4**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Hermes-2-Pro-Mistral-7B-3bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```